Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

LeCun經典論文，現在才分析，罪過罪過 摘：本文其實通過卷積神經網絡得到一個立體匹配成本stereo matching cost，而後面則是一系列的後處理：cross-based cost aggregation, semiglobal matching, a left-right consistency check, subpixel enhancement,a median filter,

>>阅读原文<<